Cl datasets - PyTorch image dataloaders and utility functions to load datasets for supervised continual learning

Overview

Continual learning datasets

Introduction

This repository contains PyTorch image dataloaders and utility functions to load datasets for supervised continual learning. Currently supported datasets:

  • MNIST
  • Pairwise-MNIST
  • Fashion-MNIST
  • not-MNIST (letters version of MNIST, see EMNIST for more detail)
  • CIFAR-10
  • CIFAR-100
  • German Traffic Signs
  • Street View House Numbers (SVHN)
  • Incremental CIFAR-100
  • Incremental TinyImageNet

Features

The provided interface simplifies typical data loading for supervised continual learning scenarios.

  • Dataset order, additional training data (for replay buffers) and test data (for global metrics computation) can all be specified.

  • A batch balancing feature is also available to make sure data from all available classes are available in a training batch.

  • Training data size and channels can be specified. Transformations will be added to make sure input data always has the same size and number of channels. If a single channel is specified, grayscaling will be applied. Otherwise, if 3 channels are specified, single channels will be triplicated. Bicubic interpolation or linear subsampling will be applied to meet the specified size.

Installation

  1. Clone the repository to your machine.
  2. Install the package:
pip install -e cl_datasets/

Note: Please use Python 3.8 or above.

Example

from cl_datasets import getDatasets

datasets = ['svhn','cifar10','fashion','mnist']
batchSize = 32
dataSize = (32,32)
nChannels = 3

dataloaders = getDatasets(datasets,batchSize,dataSize,nChannels)

for train_test_loaders in dataloaders:
    trainLoader,testLoader = train_test_loaders
    ...

List of possible datasets for training tasks

Full datasets

Description Dataset string
MNIST "mnist" or "MNIST"
not-MNIST "notMnist" or "notMNIST"
Fashion MNIST "fashion"
SVHN "svhn"
Cifar-10 "cifar10"
Cifar-100 "cifar100"
German traffic signs "traffic"

Incremental datasets

Description Dataset string
Pairwise MNIST "mnist_xy" (e.g. "mnist_01")
Incremental Cifar-100 (10 classes per task) "cifar100_i" (e.g. "cifar100_4")
Incremental Tiny ImageNet (10 classes per task) "TIN_i" (e.g. "TIN_3")
You might also like...
Project looking into use of autoencoder for semi-supervised learning and comparing data requirements compared to supervised learning.

Project looking into use of autoencoder for semi-supervised learning and comparing data requirements compared to supervised learning.

A Python library that enables ML teams to share, load, and transform data in a collaborative, flexible, and efficient way :chestnut:
A Python library that enables ML teams to share, load, and transform data in a collaborative, flexible, and efficient way :chestnut:

Squirrel Core Share, load, and transform data in a collaborative, flexible, and efficient way What is Squirrel? Squirrel is a Python library that enab

CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation (ACMMM'21 Oral Paper)
CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation (ACMMM'21 Oral Paper)

CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation (ACMMM'21 Oral Paper) (Accepted for oral presentation at ACM

ICSS - Interactive Continual Semantic Segmentation

Presentation This repository contains the code of our paper: Weakly-supervised c

[CVPR 2022] CoTTA Code for our CVPR 2022 paper Continual Test-Time Domain Adaptation

CoTTA Code for our CVPR 2022 paper Continual Test-Time Domain Adaptation Prerequisite Please create and activate the following conda envrionment. To r

[CVPR2022] Representation Compensation Networks for Continual Semantic Segmentation
[CVPR2022] Representation Compensation Networks for Continual Semantic Segmentation

RCIL [CVPR2022] Representation Compensation Networks for Continual Semantic Segmentation Chang-Bin Zhang1, Jia-Wen Xiao1, Xialei Liu1, Ying-Cong Chen2

Additional code for Stable-baselines3 to load and upload models from the Hub.

Hugging Face x Stable-baselines3 A library to load and upload Stable-baselines3 models from the Hub. Installation With pip Examples [Todo: add colab t

An easy way to build PyTorch datasets. Modularly build datasets and automatically cache processed results

EasyDatas An easy way to build PyTorch datasets. Modularly build datasets and automatically cache processed results Installation pip install git+https

A resource for learning about deep learning techniques from regression to LSTM and Reinforcement Learning using financial data and the fitness functions of algorithmic trading

A tour through tensorflow with financial data I present several models ranging in complexity from simple regression to LSTM and policy networks. The s

Owner
berjaoui
Senior Research Engineer
berjaoui
CL-Gym: Full-Featured PyTorch Library for Continual Learning

CL-Gym: Full-Featured PyTorch Library for Continual Learning CL-Gym is a small yet very flexible library for continual learning research and developme

Iman Mirzadeh 36 Dec 25, 2022
PyTorch implementation of our Adam-NSCL algorithm from our CVPR2021 (oral) paper "Training Networks in Null Space for Continual Learning"

Adam-NSCL This is a PyTorch implementation of Adam-NSCL algorithm for continual learning from our CVPR2021 (oral) paper: Title: Training Networks in N

Shipeng Wang 34 Dec 21, 2022
Pytorch Implementation of Continual Learning With Filter Atom Swapping (ICLR'22 Spolight) Paper

Continual Learning With Filter Atom Swapping Pytorch Implementation of Continual Learning With Filter Atom Swapping (ICLR'22 Spolight) Paper If find t

null 11 Aug 29, 2022
Official Pytorch implementation of Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference (ICLR 2022)

The Official Implementation of CLIB (Continual Learning for i-Blurry) Online Continual Learning on Class Incremental Blurry Task Configuration with An

NAVER AI 34 Oct 26, 2022
PyTorch implementation of: Michieli U. and Zanuttigh P., "Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations", CVPR 2021.

Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations This is the official PyTorch implementation

Multimedia Technology and Telecommunication Lab 42 Nov 9, 2022
Load What You Need: Smaller Multilingual Transformers for Pytorch and TensorFlow 2.0.

Smaller Multilingual Transformers This repository shares smaller versions of multilingual transformers that keep the same representations offered by t

Geotrend 79 Dec 28, 2022
Official code of CVPR 2021's PLOP: Learning without Forgetting for Continual Semantic Segmentation

PLOP: Learning without Forgetting for Continual Semantic Segmentation This repository contains all of our code. It is a modified version of Cermelli e

Arthur Douillard 116 Dec 14, 2022
Avalanche RL: an End-to-End Library for Continual Reinforcement Learning

Avalanche RL: an End-to-End Library for Continual Reinforcement Learning Avalanche Website | Getting Started | Examples | Tutorial | API Doc | Paper |

ContinualAI 43 Dec 24, 2022
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019). A PyTorch implementation.

Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set —— PyTorch implementation This is an unofficial offici

Sicheng Xu 833 Dec 28, 2022
Unified Pre-training for Self-Supervised Learning and Supervised Learning for ASR

UniSpeech The family of UniSpeech: UniSpeech (ICML 2021): Unified Pre-training for Self-Supervised Learning and Supervised Learning for ASR UniSpeech-

Microsoft 282 Jan 9, 2023